Smooth Inter-layer Propagation of Stabilized Neural Networks for Classification
Machine Learning
2018-10-02 v2 Artificial Intelligence
Machine Learning
Abstract
Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification. We examine batch normalization on the one hand and the dynamical systems view of residual networks on the other hand. Our goal is in understanding the notions of stability and smoothness of the inter-layer propagation of ResNets so as to explain when they contribute to significantly enhanced performance. We postulate that such stability is of importance for the trained ResNet to transfer.
Cite
@article{arxiv.1809.10315,
title = {Smooth Inter-layer Propagation of Stabilized Neural Networks for Classification},
author = {Jingfeng Zhang and Laura Wynter},
journal= {arXiv preprint arXiv:1809.10315},
year = {2018}
}
Comments
Revised Abstract